Add xx_udv25_oldfrenchsrcmf_trf-0.0.1

.gitattributes

@@ -25,3 +25,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.whl filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*strings.json filter=lfs diff=lfs merge=lfs -text
+vectors filter=lfs diff=lfs merge=lfs -text
+model filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,4 @@
+The treebank is licensed under the Creative Commons License Attribution-ShareAlike 4.0 International.
+
+The complete license text is available at:
+http://creativecommons.org/licenses/by-sa/4.0/legalcode

config.cfg

@@ -0,0 +1,254 @@
+[paths]
+train = "corpus/UD_Old_French-SRCMF/train.spacy"
+dev = "corpus/UD_Old_French-SRCMF/dev.spacy"
+vectors = null
+init_tok2vec = null
+tokenizer_source = "training/UD_Old_French-SRCMF/tokenizer/model-best"
+transformer_source = "training/UD_Old_French-SRCMF/transformer/model-best"
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "xx"
+pipeline = ["experimental_char_ner_tokenizer","transformer","senter","tagger","morphologizer","parser","experimental_edit_tree_lemmatizer"]
+batch_size = 64
+disabled = ["senter"]
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy-experimental.char_pretokenizer.v1"}
+
+[components]
+
+[components.experimental_char_ner_tokenizer]
+factory = "experimental_char_ner_tokenizer"
+scorer = {"@scorers":"spacy-experimental.tokenizer_scorer.v1"}
+
+[components.experimental_char_ner_tokenizer.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.experimental_char_ner_tokenizer.model.tok2vec]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.experimental_char_ner_tokenizer.model.tok2vec.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = 128
+attrs = ["ORTH","LOWER","IS_DIGIT","IS_ALPHA","IS_SPACE","IS_PUNCT"]
+rows = [1000,500,50,50,50,50]
+include_static_vectors = false
+
+[components.experimental_char_ner_tokenizer.model.tok2vec.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 128
+depth = 4
+window_size = 4
+maxout_pieces = 2
+
+[components.experimental_edit_tree_lemmatizer]
+factory = "experimental_edit_tree_lemmatizer"
+backoff = "orth"
+min_tree_freq = 1
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 1
+
+[components.experimental_edit_tree_lemmatizer.model]
+@architectures = "spacy.Tagger.v1"
+nO = null
+
+[components.experimental_edit_tree_lemmatizer.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+
+[components.morphologizer]
+factory = "morphologizer"
+extend = false
+overwrite = false
+scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
+
+[components.morphologizer.model]
+@architectures = "spacy.Tagger.v1"
+nO = null
+
+[components.morphologizer.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+
+[components.parser]
+factory = "parser"
+learn_tokens = false
+min_action_freq = 5
+moves = null
+scorer = {"@scorers":"spacy.parser_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.parser.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "parser"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 3
+use_upper = false
+nO = null
+
+[components.parser.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+
+[components.senter]
+factory = "senter"
+overwrite = false
+scorer = {"@scorers":"spacy.senter_scorer.v1"}
+
+[components.senter.model]
+@architectures = "spacy.Tagger.v1"
+nO = null
+
+[components.senter.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+
+[components.tagger]
+factory = "tagger"
+neg_prefix = "!"
+overwrite = false
+scorer = {"@scorers":"spacy.tagger_scorer.v1"}
+
+[components.tagger.model]
+@architectures = "spacy.Tagger.v1"
+nO = null
+
+[components.tagger.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+upstream = "transformer"
+pooling = {"@layers":"reduce_mean.v1"}
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "xlm-roberta-base"
+mixed_precision = true
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+train_corpus = "corpora.train"
+dev_corpus = "corpora.dev"
+seed = ${system:seed}
+gpu_allocator = ${system:gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 3
+patience = 5000
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+before_to_disk = null
+annotating_components = []
+
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+get_length = null
+size = 2000
+buffer = 256
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = true
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+token_f = 0.0
+token_p = null
+token_r = null
+token_acc = null
+sents_f = 0.05
+sents_p = 0.0
+sents_r = 0.0
+tag_acc = 0.11
+pos_acc = 0.05
+morph_acc = 0.05
+morph_per_feat = null
+dep_uas = 0.11
+dep_las = 0.11
+dep_las_per_type = null
+lemma_acc = 0.52
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]

experimental_char_ner_tokenizer/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

experimental_char_ner_tokenizer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32150f9486c4799acfd9ee89daaa16f056286fb250ddbe286fc92334a91ffe48
+size 6922248

experimental_char_ner_tokenizer/moves

@@ -0,0 +1 @@
+��moves�l{"0":{},"1":{"TOKEN":528469},"2":{"TOKEN":528469},"3":{"TOKEN":528469},"4":{"TOKEN":528469,"":1},"5":{"":1}}�cfg��neg_key�

experimental_edit_tree_lemmatizer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b1f84cedcbd3a14332e24af8a403277555e36ffe17126d09bf90fdba031a4e
+size 49385781

morphologizer/cfg

@@ -0,0 +1,122 @@
+{
+  "extend":false,
+  "labels_morph":{
+    "POS=CCONJ":"",
+    "Definite=Def|POS=DET|PronType=Art":"Definite=Def|PronType=Art",
+    "POS=NOUN":"",
+    "POS=PRON|PronType=Prs":"PronType=Prs",
+    "POS=VERB|VerbForm=Fin":"VerbForm=Fin",
+    "POS=PROPN":"",
+    "POS=PRON|PronType=Prs,Rel":"PronType=Prs,Rel",
+    "POS=ADV":"",
+    "POS=ADP":"",
+    "POS=ADV|PronType=Dem":"PronType=Dem",
+    "POS=PRON|PronType=Dem":"PronType=Dem",
+    "POS=VERB|Tense=Past|VerbForm=Part":"Tense=Past|VerbForm=Part",
+    "POS=AUX|VerbForm=Fin":"VerbForm=Fin",
+    "POS=DET|PronType=Int":"PronType=Int",
+    "POS=ADJ":"",
+    "POS=PRON|PronType=Ind":"PronType=Ind",
+    "POS=DET|PronType=Ind":"PronType=Ind",
+    "Morph=VPar|POS=ADJ":"Morph=VPar",
+    "POS=DET|Poss=Yes":"Poss=Yes",
+    "POS=ADV|Polarity=Neg":"Polarity=Neg",
+    "Definite=Def|POS=ADP|PronType=Art":"Definite=Def|PronType=Art",
+    "POS=PRON|PronType=Int":"PronType=Int",
+    "POS=SCONJ":"",
+    "POS=VERB|VerbForm=Inf":"VerbForm=Inf",
+    "NumType=Card|POS=PRON":"NumType=Card",
+    "POS=PRON":"",
+    "NumType=Card|POS=DET":"NumType=Card",
+    "POS=PRON|Polarity=Neg|PronType=Prs":"Polarity=Neg|PronType=Prs",
+    "POS=ADJ|Poss=Yes":"Poss=Yes",
+    "POS=PRON|Poss=Yes|PronType=Prs":"Poss=Yes|PronType=Prs",
+    "Definite=Ind|POS=DET|PronType=Art":"Definite=Ind|PronType=Art",
+    "POS=DET|PronType=Dem":"PronType=Dem",
+    "POS=AUX|VerbForm=Inf":"VerbForm=Inf",
+    "POS=ADJ|PronType=Ind":"PronType=Ind",
+    "Morph=VPar|POS=NOUN":"Morph=VPar",
+    "POS=VERB|Tense=Pres|VerbForm=Part":"Tense=Pres|VerbForm=Part",
+    "Morph=VPar|POS=PROPN":"Morph=VPar",
+    "Morph=VInf|POS=NOUN":"Morph=VInf",
+    "NumType=Ord|POS=PRON":"NumType=Ord",
+    "POS=INTJ":"",
+    "POS=SCONJ|PronType=Prs":"PronType=Prs",
+    "Morph=VFin|POS=NOUN":"Morph=VFin",
+    "POS=DET|PronType=Rel":"PronType=Rel",
+    "NumType=Card|POS=ADJ":"NumType=Card",
+    "POS=ADJ|PronType=Ord":"PronType=Ord",
+    "Morph=VFin|POS=ADV":"Morph=VFin",
+    "Morph=VFin|POS=PROPN":"Morph=VFin",
+    "POS=DET":"",
+    "Morph=VPar|POS=ADP":"Morph=VPar",
+    "Morph=VPar|POS=ADV":"Morph=VPar",
+    "NumType=Ord|POS=DET":"NumType=Ord",
+    "Morph=VFin|POS=ADP":"Morph=VFin",
+    "Morph=VFin|POS=CCONJ":"Morph=VFin",
+    "Morph=VInf|POS=ADJ":"Morph=VInf",
+    "POS=ADP|PronType=Dem":"PronType=Dem",
+    "POS=ADV|Polarity=Int":"Polarity=Int",
+    "Morph=VFin|POS=INTJ":"Morph=VFin"
+  },
+  "labels_pos":{
+    "POS=CCONJ":89,
+    "Definite=Def|POS=DET|PronType=Art":90,
+    "POS=NOUN":92,
+    "POS=PRON|PronType=Prs":95,
+    "POS=VERB|VerbForm=Fin":100,
+    "POS=PROPN":96,
+    "POS=PRON|PronType=Prs,Rel":95,
+    "POS=ADV":86,
+    "POS=ADP":85,
+    "POS=ADV|PronType=Dem":86,
+    "POS=PRON|PronType=Dem":95,
+    "POS=VERB|Tense=Past|VerbForm=Part":100,
+    "POS=AUX|VerbForm=Fin":87,
+    "POS=DET|PronType=Int":90,
+    "POS=ADJ":84,
+    "POS=PRON|PronType=Ind":95,
+    "POS=DET|PronType=Ind":90,
+    "Morph=VPar|POS=ADJ":84,
+    "POS=DET|Poss=Yes":90,
+    "POS=ADV|Polarity=Neg":86,
+    "Definite=Def|POS=ADP|PronType=Art":85,
+    "POS=PRON|PronType=Int":95,
+    "POS=SCONJ":98,
+    "POS=VERB|VerbForm=Inf":100,
+    "NumType=Card|POS=PRON":95,
+    "POS=PRON":95,
+    "NumType=Card|POS=DET":90,
+    "POS=PRON|Polarity=Neg|PronType=Prs":95,
+    "POS=ADJ|Poss=Yes":84,
+    "POS=PRON|Poss=Yes|PronType=Prs":95,
+    "Definite=Ind|POS=DET|PronType=Art":90,
+    "POS=DET|PronType=Dem":90,
+    "POS=AUX|VerbForm=Inf":87,
+    "POS=ADJ|PronType=Ind":84,
+    "Morph=VPar|POS=NOUN":92,
+    "POS=VERB|Tense=Pres|VerbForm=Part":100,
+    "Morph=VPar|POS=PROPN":96,
+    "Morph=VInf|POS=NOUN":92,
+    "NumType=Ord|POS=PRON":95,
+    "POS=INTJ":91,
+    "POS=SCONJ|PronType=Prs":98,
+    "Morph=VFin|POS=NOUN":92,
+    "POS=DET|PronType=Rel":90,
+    "NumType=Card|POS=ADJ":84,
+    "POS=ADJ|PronType=Ord":84,
+    "Morph=VFin|POS=ADV":86,
+    "Morph=VFin|POS=PROPN":96,
+    "POS=DET":90,
+    "Morph=VPar|POS=ADP":85,
+    "Morph=VPar|POS=ADV":86,
+    "NumType=Ord|POS=DET":90,
+    "Morph=VFin|POS=ADP":85,
+    "Morph=VFin|POS=CCONJ":89,
+    "Morph=VInf|POS=ADJ":84,
+    "POS=ADP|PronType=Dem":85,
+    "POS=ADV|Polarity=Int":86,
+    "Morph=VFin|POS=INTJ":91
+  },
+  "overwrite":false
+}

morphologizer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e73db06b05ece5c866a667df334dffed78ba3b827ce6d56b288a93603402e3
+size 175922

parser/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":5,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

parser/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a12f578d04f09895cbfe7c4df4d516eb685e09d9283a6a2b8b31ae478690c96
+size 1066773

parser/moves

@@ -0,0 +1 @@
+��moves�{"0":{"":87656},"1":{"":34458},"2":{"det":13130,"case":10431,"advmod":10283,"nsubj":10275,"obj":6311,"mark":5679,"obl":5122,"cc:nc":4602,"cc":3674,"aux":3042,"amod":2408,"iobj":2387,"cop":1892,"case:det":1682,"advcl":1182,"expl":1100,"obl:advmod":934,"vocative":683,"nummod":550,"xcomp":282,"parataxis":273,"aux:pass":246,"obj||xcomp":233,"advmod||obj":149,"nmod":115,"discourse":111,"acl":111,"dislocated":92,"obl||xcomp":76,"nsubj:obj":64,"csubj":53,"iobj||xcomp":41,"nmod||obj":40,"advmod||advcl":37,"advmod||obl":26,"advmod||nsubj":25,"ccomp":17,"appos":15,"advmod||advmod":14,"advcl||aux":13,"amod||obj":12,"mark||obj":11,"mark:obl":10,"nmod||nsubj":8,"obj||ccomp":7,"mark:advmod":7,"expl||xcomp":7,"obj:advmod":6,"mark:obj":6,"amod||nsubj":6,"advmod||xcomp":6,"acl:relcl||nsubj":6,"xcomp||xcomp":5,"obl||ccomp":5,"obl:advmod||xcomp":5,"acl||nsubj":5,"dep":0},"3":{"obl":5765,"obj":4256,"conj":3520,"advmod":2800,"nsubj":2482,"nmod":2075,"advcl":1842,"acl:relcl":1837,"xcomp":1701,"ccomp":1063,"amod":972,"acl":880,"flat":822,"appos":466,"cop":460,"aux":392,"iobj":364,"conj||obj":223,"conj||nsubj":175,"acl:relcl||nsubj":167,"acl||obj":142,"csubj":140,"conj||obl":130,"vocative":114,"acl:relcl||obj":110,"cc||conj":107,"parataxis":98,"expl":96,"amod||obj":80,"acl||nsubj":78,"dislocated":72,"nmod||advmod":65,"obl:advmod":59,"acl:relcl||obl":56,"advcl||amod":51,"acl||obl":48,"amod||nsubj":44,"nmod||obj":42,"case":30,"conj||amod":27,"aux:pass":26,"conj||xcomp":21,"advcl||aux":21,"fixed||mark":20,"advmod||obj":20,"obl||xcomp":19,"nummod":19,"conj||advmod":19,"ccomp||aux":19,"appos||nsubj":18,"advcl||advmod":18,"conj||aux":16,"nmod||nsubj":13,"nmod||amod":13,"appos||obj":13,"det":12,"conj||iobj":12,"obj||xcomp":11,"conj||case":11,"acl||amod":10,"acl:relcl||conj":10,"mark":9,"cc":9,"acl||conj":8,"obl||advmod":7,"conj||nummod":7,"conj||conj":7,"acl||expl":7,"acl:relcl||nmod":7,"advmod||xcomp":6,"advmod||advmod":6,"xcomp||xcomp":5,"nmod||obl":5,"ccomp||xcomp":5,"amod||obl":5,"advmod||nsubj":5,"advmod||advcl":5,"advcl||obj":5,"dep":0},"4":{"ROOT":13909}}�cfg��neg_key�

senter/cfg

@@ -0,0 +1,3 @@
+{
+  "overwrite":false
+}

senter/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9c8a175597d5d1bb8e9593f8f10ce42a9c146bc23e7f76bd53970e2cfefa49
+size 6740

tagger/cfg

@@ -0,0 +1,66 @@
+{
+  "labels":[
+    "ADJQUA",
+    "ADJcar",
+    "ADJind",
+    "ADJord",
+    "ADJpos",
+    "ADJqua",
+    "ADVgen",
+    "ADVgen.PROadv",
+    "ADVgen.PROper",
+    "ADVing",
+    "ADVint",
+    "ADVneg",
+    "ADVneg.PROper",
+    "ADVsub",
+    "CONcoo",
+    "CONsub",
+    "CONsub.PROper",
+    "CONsub_o",
+    "CONsub_pre",
+    "DETcar",
+    "DETdef",
+    "DETdem",
+    "DETind",
+    "DETint",
+    "DETndf",
+    "DETord",
+    "DETpos",
+    "DETrel",
+    "DETrel_o",
+    "ETR",
+    "INJ",
+    "NOMcom",
+    "NOMcom.PROper",
+    "NOMpro",
+    "PRE",
+    "PRE.DETdef",
+    "PRE.PROdem",
+    "PRE.PROper",
+    "PROadv",
+    "PROcar",
+    "PROdem",
+    "PROimp",
+    "PROind",
+    "PROint",
+    "PROint.PROper",
+    "PROint_adv",
+    "PROord",
+    "PROper",
+    "PROper.PROper",
+    "PROpos",
+    "PROrel",
+    "PROrel.ADVneg",
+    "PROrel.PROadv",
+    "PROrel.PROper",
+    "PROrel_adv",
+    "RED",
+    "VERcjg",
+    "VERinf",
+    "VERppa",
+    "VERppe"
+  ],
+  "neg_prefix":"!",
+  "overwrite":false
+}

tagger/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd48f2365ce10d1738c6d261b6a765853459d37370e7edf17b5112161802b48d
+size 185150

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:690b268a649be18f30586a1dfac4d0d4fb719731f025d9b6b75a3d47b478a3af
+size 1126406104

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/strings.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288c67639baa41bedcaf72c2e5fea0ce9468cd59aed948f7222aca3b9aa5b83f
+size 617864

vocab/vectors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14772b683e726436d5948ad3fff2b43d036ef2ebbe3458aafed6004e05a40706
+size 128

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}

xx_udv25_oldfrenchsrcmf_trf-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776a6d5e6a0dbd54b7ee92bb06217b4d8136ff11e11a73ceddcf7edfebfac376
+size 891852582